Research Scientist, Frontier Red Team (Autonomy) - Remote

Overview

Anthropic is seeking Research Scientists to develop and implement advanced autonomy evaluations to determine the AI Safety Level (ASL) of their models, contributing to the mission of creating reliable and beneficial AI systems.

In Short

• Lead the development of autonomy evaluations and research.
• Iterate on experiments to evaluate autonomous capabilities.
• Provide technical leadership to Research Engineers.
• Communicate evaluation outcomes to relevant teams and stakeholders.
• Collaborate on projects to improve infrastructure and safety techniques.
• ML background with experience in LLMs/multimodal models.
• Strong Python engineering skills.
• Ability to solve ambiguously scoped problems.
• Experience in designing and running experiments.
• Thrive in a collaborative environment.

Requirements

• Experience in leading experimental research.
• Strong Python programming skills.
• Ability to work on machine learning problems.
• Experience with training and prompting models.
• Interest in people management (optional).

Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Collaborative office space.